[R-SIG-Finance] fPortfolio problem

Bastian Offermann bastian2507hk at yahoo.co.uk
Wed Dec 10 18:28:31 CET 2008


Hello,

i have encountered a problem with fPortfolio recently. I am using below 
code:

the problem is that my risk free rate is different from the one 
displayed in the graphical output and the straight line in the graphical 
output intersects the efficient frontier twice. same problem when i use 
"cmlLines(eff.front)" .what am i missing out on?

THanks.

Data1 <- as.timeSeries(Data1)
Data1 <- as.timeSeries(data(LPP2005REC))
Data1 <- Data1[,1:4]*250

r.p <- 0.10
r.rf <- 0.01

Spec <- portfolioSpec()
restr <- c("Short", "LongOnly")
cons <- restr[1]
setOptimize(Spec) <- "minRisk"
setRiskFreeRate(Spec) <- r.rf #/250
setTargetReturn(Spec) <- r.p #/250
setNFrontierPoints(Spec) <- 50
solver <- c("solveRquadprog", "solveRshortExact")
if(cons == "LongOnly") { setSolver(Spec) <- solver[1] }
if(cons == "Short") { setSolver(Spec) <- solver[2] }

eff.front <- portfolioFrontier(data = Data1, spec = Spec, constraints = 
cons)
eff.port <- efficientPortfolio(data = Data1, spec = Spec, constraints = 
cons)
tang.port <- tangencyPortfolio(data = Data1, spec = Spec, constraints = 
cons)
minvar.port <- minvariancePortfolio(data = Data1, spec = Spec, 
constraints = cons)
w <- as.vector(getWeights(eff.port))
w <- matrix(w, 1, ncol(Data1))
w.min <- as.vector(getWeights(minvar.port))
w.min <- matrix(w.min, 1, ncol(Data1))
w
w.min
frontierPlot(eff.front, frontier = "upper", return="mu", risk="Sigma", 
type="l")
minvariancePoints(eff.front, col="red", bg="red", pch=21)
tangencyLines(eff.front)
tangencyPoints(eff.front)



More information about the R-SIG-Finance mailing list